Skip to contentSkip to conversation

net: rps: add the shortcut for one rps_cpus

PATCH In review Changli Gao 3 participants 4 messages Sep 4, 2010 – Sep 8, 2010

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 net: rps: add the shortcut for one rps_cpus

When there is only one rps_cpus, skb_get_rxhash() can be eliminated.

---
 net/core/dev.c |   14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)
net/core/dev.c +11 -3
index d8c43e7..2bf740c 100644
@@ -2345,7 +2345,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		       struct rps_dev_flow **rflowp)
 {
 	struct netdev_rx_queue *rxqueue;
-	struct rps_map *map;
+	struct rps_map *map = NULL;
 	struct rps_dev_flow_table *flow_table;
 	struct rps_sock_flow_table *sock_flow_table;
 	int cpu = -1;
@@ -2363,8 +2363,17 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	} else
 		rxqueue = dev->_rx;
 
-	if (!rxqueue->rps_map && !rxqueue->rps_flow_table)
+	if (rxqueue->rps_map) {
+		map = rcu_dereference(rxqueue->rps_map);
+		if (map && map->len == 1) {
+			tcpu = map->cpus[0];
+			if (cpu_online(tcpu))
+				cpu = tcpu;
+			goto done;
+		}
+	} else if (!rxqueue->rps_flow_table) {
 		goto done;
+	}
 
 	skb_reset_network_header(skb);
 	if (!skb_get_rxhash(skb))
@@ -2409,7 +2418,6 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		}
 	}
 
-	map = rcu_dereference(rxqueue->rps_map);
 	if (map) {
 		tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
 
#1 lore raw
Quoted 39 lines · Changli Gao

When there is only one rps_cpus, skb_get_rxhash() can be eliminated.

---
 net/core/dev.c |   14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)
net/core/dev.c +11 -2
index d8c43e7..2bf740c 100644
@@ -2345,7 +2345,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		       struct rps_dev_flow **rflowp)
 {
 	struct netdev_rx_queue *rxqueue;
-	struct rps_map *map;
+	struct rps_map *map = NULL;
 	struct rps_dev_flow_table *flow_table;
 	struct rps_sock_flow_table *sock_flow_table;
 	int cpu = -1;
@@ -2363,8 +2363,17 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	} else
 		rxqueue = dev->_rx;
 
-	if (!rxqueue->rps_map && !rxqueue->rps_flow_table)
+	if (rxqueue->rps_map) {
+		map = rcu_dereference(rxqueue->rps_map);
+		if (map && map->len == 1) {
+			tcpu = map->cpus[0];
+			if (cpu_online(tcpu))
+				cpu = tcpu;
+			goto done;
+		}
+	} else if (!rxqueue->rps_flow_table) {
 		goto done;
+	}
 
 	skb_reset_network_header(skb);
 	if (!skb_get_rxhash(skb))

net/core/dev.c static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,

Quoted 8 lines
net/core/dev.c +0 -2
@@ -2409,7 +2418,6 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		}
 	}
 
-	map = rcu_dereference(rxqueue->rps_map);
 	if (map) {
 		tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
 
--

You are 'optimizing' a very unusual case and slow down 99% of normal uses.

Normal way to handle this, is to use irq affinity and deliver interrupts directly to the target cpu.

#2 lore raw
Quoted 7 lines · Eric Dumazet

You are 'optimizing' a very unusual case and slow down 99% of normal uses.

Normal way to handle this, is to use irq affinity and deliver interrupts directly to the target cpu.

Some pseudo network devices may share the same interrupt, such as vlan network devices. In this case, setting the IRQ affinity can't work.

Signature · 2 lines
Regards,
Changli Gao([email protected])
maintainer
#3 lore raw

From: Changli Gao <[email protected]>
Date: Sat, 4 Sep 2010 20:18:20 +0800

Quoted 11 lines · Eric Dumazet
Quoted 7 lines

You are 'optimizing' a very unusual case and slow down 99% of normal uses.

Normal way to handle this, is to use irq affinity and deliver interrupts directly to the target cpu.

Some pseudo network devices may share the same interrupt, such as vlan network devices. In this case, setting the IRQ affinity can't work.

I'm fine with this patch being in net-next-2.6 for now, so I've applied it, thanks.